✨SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models

📝 Summary:
SecureCode v2.0 is a production-grade dataset of 1215 security-focused coding examples. It trains AI models to generate secure code by providing real-incident examples with vulnerable and secure implementations, attacks, defense, and operational security context across 11 languages, using a conve...

🔹 Publication Date: Published on Dec 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.18542
• PDF: https://arxiv.org/pdf/2512.18542
• Project Page: https://perfecxion.ai/
• Github: https://github.com/scthornton/securecode-v2

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#Cybersecurity #CodeSecurity #AI #CodeGeneration #Dataset

✨Towards Automated Kernel Generation in the Era of LLMs

📝 Summary:
This survey explores how large language models and agent systems are automating kernel generation and optimization, a critical yet non-scalable process for AI systems. It provides a structured overview of existing approaches, datasets, and benchmarks, aiming to unify this fragmented field and out...

🔹 Publication Date: Published on Jan 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.15727
• PDF: https://arxiv.org/pdf/2601.15727
• Github: https://github.com/flagos-ai/awesome-LLM-driven-kernel-generation

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLMs #KernelGeneration #AI #Automation #CodeGeneration

✨GoodVibe: Security-by-Vibe for LLM-Based Code Generation

📝 Summary:
GoodVibe secures LLM-generated code by precisely fine-tuning only a small subset of security-relevant neurons. This neuron-level framework greatly enhances code security and preserves utility with significantly fewer parameters and training costs than traditional methods.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10778
• PDF: https://arxiv.org/pdf/2602.10778

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLM #CodeGeneration #Cybersecurity #AIsecurity #MachineLearning

✨Code2Worlds: Empowering Coding LLMs for 4D World Generation

📝 Summary:
Code2Worlds empowers coding LLMs to generate 4D dynamic scenes by formulating it as language-to-simulation code. It uses a dual-stream architecture and physics-aware closed-loop refinement to ensure physical fidelity. The system significantly outperforms baselines, uniquely generating realistic, ...

🔹 Publication Date: Published on Feb 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11757
• PDF: https://arxiv.org/pdf/2602.11757
• Project Page: https://aigeeksgroup.github.io/Code2Worlds
• Github: https://aigeeksgroup.github.io/Code2Worlds

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLM #CodeGeneration #4DGeneration #AISimulation #Research

✨Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

📝 Summary:
Nanbeige4.1-3B is a 3B-parameter model excelling in agentic behavior, code generation, and reasoning. It outperforms larger models through advanced reward modeling and training, demonstrating broad competence for a small language model.

🔹 Publication Date: Published on Feb 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.13367
• PDF: https://arxiv.org/pdf/2602.13367
• Project Page: https://huggingface.co/Nanbeige/Nanbeige4.1-3B

🔹 Models citing this paper:
• https://huggingface.co/Nanbeige/Nanbeige4.1-3B

✨ Spaces citing this paper:
• https://huggingface.co/spaces/PioTio/AIMan

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLM #AI #SmallLanguageModels #AgenticAI #CodeGeneration

✨TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

📝 Summary:
TAROT proposes a reinforcement fine-tuning method for code generation that uses a four-tier test suite and capability-adaptive curriculum. This approach tailors curriculum progression based on a models skill, improving functional correctness and robustness.

🔹 Publication Date: Published on Feb 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.15449
• PDF: https://arxiv.org/pdf/2602.15449
• Github: https://github.com/deep-diver/TAROT

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLM #CodeGeneration #ReinforcementLearning #AI #MachineLearning

✨CL4SE: A Context Learning Benchmark For Software Engineering Tasks

📝 Summary:
CL4SE presents a benchmark for evaluating context learning in software engineering tasks, defining four SE-specific context types. It demonstrates an average 24.7% performance improvement for LLMs across tasks like code generation and review, establishing a standardized evaluation framework.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23047
• PDF: https://arxiv.org/pdf/2602.23047
• Project Page: https://huggingface.co/papers?q=project-specific%20context
• Github: https://github.com/Tomsawyerhu/CodeCL

✨ Datasets citing this paper:
• https://huggingface.co/datasets/tomhu/codecl

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#ContextLearning #SoftwareEngineering #LLMs #CodeGeneration #Benchmarks

✨V_1: Unifying Generation and Self-Verification for Parallel Reasoners

📝 Summary:
V1 unifies generation and verification for complex reasoning tasks. It leverages models' superior ability in pairwise self-verification over independent scoring, improving performance and efficiency in code generation and math.

🔹 Publication Date: Published on Mar 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.04304
• PDF: https://arxiv.org/pdf/2603.04304
• Project Page: https://harmandotpy.github.io/v1-verification/
• Github: https://github.com/HarmanDotpy/pairwise-self-verification

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #LLMs #MachineLearning #CodeGeneration #AIReasoning

✨ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

📝 Summary:
ReflexiCoder uses reinforcement learning to teach large language models autonomous code reflection and self-correction. It internalizes the debugging process into the model, achieving state-of-the-art performance on coding benchmarks, rivaling proprietary models, and reducing inference compute by...

🔹 Publication Date: Published on Mar 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.05863
• PDF: https://arxiv.org/pdf/2603.05863
• Github: https://github.com/juyongjiang/ReflexiCoder

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#LLM #ReinforcementLearning #CodeGeneration #AI #DeepLearning

✨CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

📝 Summary:
Researchers introduced CreativeBench, a benchmark for evaluating machine creativity in code generation using a quality-novelty metric. They found scaling improves combinatorial creativity but yields diminishing returns for exploration. They also proposed EvoRePE, an inference-time strategy to enh...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11863
• PDF: https://arxiv.org/pdf/2603.11863
• Project Page: https://zethwang.github.io/creativebench.github.io/
• Github: https://github.com/ZethWang/CreativeBench

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#MachineCreativity #CodeGeneration #AIBenchmark #GenerativeAI #AIResearch